INDEX

Explanations

phrases or words that indicate a sense of completeness or totality

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Miquel

-0.73

jangkau

-0.65

 Kontakte

-0.64

lalu

-0.63

 esetben

-0.63

nameLabel

-0.62

@[+][

-0.62

 طويلة

-0.60

 רבים

-0.59

Lieferumfang

-0.59

POSITIVE LOGITS

 totally

1.36

 Totally

1.35

 completely

1.32

 Completely

1.31

Totally

1.24

Completely

1.20

totally

1.15

completely

1.13

 entirely

1.04

 utterly

1.02

Activations Density 0.098%

phrases or words that indicate a sense of completeness or totality

No Comments

No Known Activations